© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 55976
    Prev
    Next
    INDEX
    Explanations

    because

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĶĺ
    -0.09
    ä¸Ģåı·
    -0.08
    зе
    -0.08
    ä¿Ń
    -0.08
    æĸ°åĵģ
    -0.08
    elim
    -0.08
    emes
    -0.08
    ä¸ĭåįĬåľº
    -0.08
    å¸ĸ
    -0.08
    onso
    -0.08
    POSITIVE LOGITS
    å¢ŀåĢ¼æľįåĬ¡
    0.09
    éĤij
    0.09
    ramer
    0.09
    åıijæĮ¥ä½ľçĶ¨
    0.09
    æĬ¬å¤´
    0.08
    奢ä¾Ī
    0.08
    OUCH
    0.08
    åıijæĮ¥äºĨ
    0.08
    rms
    0.08
     mig
    0.08
    Activations Density 0.171%

    No Known Activations